Surface Reconstruction From Point Clouds via Image-Free Point-to-Gaussian Inference
- 1 July 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 6379-6390
Abstract
The task of surface reconstruction from point clouds is to produce high-quality meshes using sampled 3D points (no images available). Traditional methods primarily focus on geometric accuracy but often produce meshes without texture colors. In this paper, we present a brand-new perspective in point cloud reconstruction task-Imagining points as more informative Gaussian splats and obtaining colored surfaces through free-form Gaussian-rendering reconstruction. We train a universal Point-to-Gaussian model to infer the attributes of Gaussian splats for any given pointcloud with merely point coordinates (and color optionally) as input, without requiring any image. Significant technical designs are applied on initialization, regularization and loss functions, making the whole learning process stable. The inferred Gaussian splats can faithfully recover the original appearance of objects or scenes (capable of quick rendering from any viewpoint, like human's imagination ability), meanwhile closely adhering to the input shape. After obtaining a sufficient number of virtually rendered images and depth maps, we employ the truncated signed distance function (TSDF) fusion to get the reconstruction results, producing high-quality and colored meshes. Extensive experiments demonstrate that our approach surpasses state-of-the-art methods in surface reconstruction metrics while maintaining high efficiency and simplicity.Keywords
Funding Information
- National Natural Science Foundation of China (62502195)
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China (JYB2025XDXM118)
- Nanjing Major Science and Technology Special (202209003)
This publication has 61 references indexed in Scilit:
- Drivable 3D Gaussian Avatars2025
- Capturing, Reconstructing, and Simulating: The UrbanScene3D Dataset2022
- Big earth data for achieving the sustainable development goals in the belt and road regionBig Earth Data, 2022
- ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds2020
- Points2Surf Learning Implicit Surfaces from Point Clouds2020
- Matterport3D: Learning from RGB-D Data in Indoor Environments2017
- Surface reconstruction by computing restricted Voronoi cells in parallelComputer-Aided Design, 2017
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Structure-from-Motion Revisited2016
- Principal component analysisWIREs Computational Statistics, 2010